References
[1] ANAN T HANARAYANA N ,G.,GHODSI,A.,SHENKER,
S., AND STO IC A, I. Disk-locality in datacenter com-
puting considered irrelevant. In HotOS (2011).
[2] ANAN T HANARAYANA N ,G.,HUNG,M.C.-C.,REN,
X., STO IC A,I.,WIERMAN,A.,AND YU, M. Grass:
Trimming stragglers in approximation analytics. In
NSDI (2014).
[3] ANAN T HANARAYANA N ,G.,KANDULA,S.,GREEN-
BERG,A.,STO ICA ,I.,LU,Y.,SAHA,B.,AND HAR-
RIS, E. Reining in the Outliers in Map-Reduce Clusters
using Mantri. In Proc. OSDI (2010).
[4] ANAN T HANARAYANA N ,G.,KANDULA,S.,GREEN-
BERG,A.,STO ICA ,I.,LU,Y.,SAHA,B.,AND HAR-
RIS, E. Reining in the outliers in map-reduce clusters
using mantri. In OSDI (2010).
[5] Amazon Athena. http://aws.amazon.com/
athena/.
[6] Serverless Reference Architecture: MapRe-
duce. https://github.com/awslabs/
lambda-refarch-mapreduce.
[7] Azure Blob Storage Request Limits. https://cloud.
google.com/storage/docs/request-rate.
[8] Big Data Benchmark. https://amplab.cs.
berkeley.edu/benchmark/.
[9] Google BigQuery. https://cloud.google.com/
bigquery/.
[10] BONCZ,P.A.,MANEGOLD,S.,AND KERSTEN,
M. L. Database architecture optimized for the new bot-
tleneck: Memory access. In Proceedings of the 25th
International Conference on Very Large Data Bases
(1999).
[11] CHOWDHURY,M.,AND STOIC A, I. Coflow: A Net-
working Abstraction for Cluster Applications. In Proc.
HotNets (2012), pp. 31–36.
[12] CHOWDHURY,M.,AND STO IC A, I. Coflow: A net-
working abstraction for cluster applications. In HotNets
(2012).
[13] CHOWDHURY,M.,ZHONG,Y.,AND STOI CA, I. Ef-
ficient coflow scheduling with varys. In SIGCOMM
(2014).
[14] CHU,S.,BALAZINSKA,M.,AND SUCIU, D. From
theory to practice: Efficient join query evaluation in a
parallel database system. In SIGMOD (2015).
[15] DEAN,J.,AND GHEMAWAT, S. MapReduce: Simpli-
fied Data Processing on Large Clusters. Proc. OSDI
(2004).
[16] ERIC JONAS,QIFAN PU,SHIVARAM VENKATARA-
MAN,ION STO IC A,BENJAMIN RECHT. Occupy the
Cloud: Distributed Computing for the 99%. In SoCC
(2017).
[17] ESTIVILL-CASTRO,V.,AND WOOD, D. A survey
of adaptive sorting algorithms. ACM Comput. Surv.
(1992).
[18] FOULADI,S.,WAHBY,R.S.,SHACKLETT,B.,BAL-
ASUBRAMANIAM,K.V.,ZENG,W.,BHALERAO,R.,
SIVARAMAN,A.,PORTER,G.,AND WINSTEIN,K.
Encoding, Fast and Slow: Low-Latency Video Process-
ing Using Thousands of Tiny Threads. In NSDI (2017).
[19] GAO ,P.X.,NARAYAN,A.,KARANDIKAR,S.,CAR-
REIRA,J.,HAN,S.,AGARWAL,R.,RATNAS AM Y,S.,
AND SHENKER, S. Network requirements for resource
disaggregation. In OSDI (2016).
[20] Google Cloud Storage Request Limits. https:
//docs.microsoft.com/en-us/azure/storage/
common/storage-scalability-targets.
[21] GHEMAWAT,S.,GOBIOFF,H.,AND LEUNG, S. The
Google File System. In Proc. SOSP (2003), pp. 29–43.
[22] Amazon Glue. https://aws.amazon.com/glue/.
[23] Google Cloud Dataflow Shuffle. https://cloud.
google.com/dataflow/.
[24] GRAY,J.,AND GRAEFE, G. The five-minute rule ten
years later, and other computer storage rules of thumb.
SIGMOD Rec. (1997).
[25] HENDRICKSON,S.,STURDEVANT,S.,HARTER,T.,
VENKATARAMANI,V.,ARPACI-DUSSEAU,A.C.,
AND ARPACI-DUSSEAU, R. H. Serverless computa-
tion with OpenLambda. In HotCloud (2016).
[26] Using AWS Lambda with Kinesis. http:
//docs.aws.amazon.com/lambda/latest/dg/
with-kinesis.html.
[27] LISTGARTEN,S.,AND NEIMAT, M.-A. Modelling
costs for a mm-dbms. In RTDB (1996).
[28] MANEGOLD,S.,BONCZ,P.,AND KERSTEN,M.L.
Generic database cost models for hierarchical memory
systems. In VLDB (2002).
[29] MANNINO,M.V.,CHU,P.,AND SAGER, T. Statisti-
cal profile estimation in database systems. ACM Com-
put. Surv. (1988).
USENIX Association 16th USENIX Symposium on Networked Systems Design and Implementation 205